{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/entropy-is-not-enough-for-test-time","title":"Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors","arxiv_id":"2403.07366","date":"2024-03-12","proceeding":null,"authors":["Jonghyun Lee","Dahuin Jung","Saehyung Lee","Junsung Park","Juhyeon Shin","Uiwon Hwang","Sungroh Yoon"],"abstract":"Test-time adaptation (TTA) fine-tunes pre-trained deep neural networks for unseen test data. The primary challenge of TTA is limited access to the entire test dataset during online updates, causing error accumulation. To mitigate it, TTA methods have utilized the model output's entropy as a confidence metric that aims to determine which samples have a lower likelihood of causing error. Through experimental studies, however, we observed the unreliability of entropy as a confidence metric for TTA under biased scenarios and theoretically revealed that it stems from the neglect of the influence of latent disentangled factors of data on predictions. Building upon these findings, we introduce a novel TTA method named Destroy Your Object (DeYO), which leverages a newly proposed confidence metric named Pseudo-Label Probability Difference (PLPD). PLPD quantifies the influence of the shape of an object on prediction by measuring the difference between predictions before and after applying an object-destructive transformation. DeYO consists of sample selection and sample weighting, which employ entropy and PLPD concurrently. For robust adaptation, DeYO prioritizes samples that dominantly incorporate shape information when making predictions. Our extensive experiments demonstrate the consistent superiority of DeYO over baseline methods across various scenarios, including biased and wild. Project page is publicly available at https://whitesnowdrop.github.io/DeYO/.","url_abs":"https://arxiv.org/abs/2403.07366v1","url_pdf":"https://arxiv.org/pdf/2403.07366v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"entropy-is-not-enough-for-test-time","repo_url":"https://github.com/Jhyun17/DeYO","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"pseudo-label","task_name":"Pseudo Label"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/test-time-adaptation-on-imagenet-c","task":"Test-time Adaptation","dataset":"ImageNet-C","model":"DeYO","rank_in_archive_order":1,"of":1,"metrics":{"Mean Accuracy":"48.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.07366","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07366"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Jhyun17/DeYO","reach":null}],"summary":{"ran":1,"ran_draft_wrong":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"e7c414643baf231f","entry":"DeYO","repo":"Jhyun17/DeYO","repo_kind":"official","path":"methods/deyo.py","file_url":"https://github.com/Jhyun17/DeYO/blob/HEAD/methods/deyo.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e7c414643baf231f"}},{"code_sha256_prefix":"0c7e495c41c9465c","entry":"collect_params","repo":"Jhyun17/DeYO","repo_kind":"official","path":"methods/deyo.py","file_url":"https://github.com/Jhyun17/DeYO/blob/HEAD/methods/deyo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c7e495c41c9465c"}},{"code_sha256_prefix":"99ffb7c9f7a79773","entry":"forward_and_adapt_deyo","repo":"Jhyun17/DeYO","repo_kind":"official","path":"methods/deyo.py","file_url":"https://github.com/Jhyun17/DeYO/blob/HEAD/methods/deyo.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"99ffb7c9f7a79773"}},{"code_sha256_prefix":"3078648c75e3e1e3","entry":"softmax_entropy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3078648c75e3e1e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}